done between the server and user and a symmetric key is generated on both sides, which ... in a variety of security, access control and monitoring applications. ... Authentication and Key Exchange protocols, which are based on passwords [4].
P.Tamil Selvi et al. / (IJCSE) International Journal on Computer Science and Engineering Vol. 02, No. 08, 2010, 2652-2658
MULTIMODAL BIOMETRICS BASED AUTHENTICATION AGAINST DICTIONARY ATTACKS P.Tamil Selvi,1 1
Research Scholar, P.S.G.R.Krishnammal College for women, Bharathiar University, Coimbatore, India
Abstract—The Multimodal Biometric based user authentication systems are highly secured and efficient to use and place total trust on the authentication server where biometric verification data are stored in a central database. Such systems are, prone to dictionary attacks initiated at the server side. In this paper, we propose an efficient approach based on multimodal biometrics (Iris and fingerprint) based user authentication and key exchange system. In this system, minutiae points and texture properties are extracted from the fingerprint and iris images are stored in the encrypted form in the server’s database, to overcome the dictionary attacks mounted by the server. The image processing techniques are used to extract a biometric measurement from the fingerprint and iris. During login procedure the mutual authentication is done between the server and user and a symmetric key is generated on both sides, which could be used for further secure communication between them. Thus meet-in-the middle attack that happens between the user and the server can also be overcome. This system can be directly applied to strengthen existing password or biometric based systems without requiring additional computation. Keywords- Authentication, Dictionary Attack, Fingerprint, Fusion, Iris, Key Exchange, Minutiae points.
N.Radha2 2
Sr.Lecturer, P.S.G.R.Krishnammal College for women, Bharathiar University, Coimbatore, India
applications. Biometric systems that generally employ a single attribute for recognition (unimodal biometric systems) are influenced by some practical issues like noisy sensor data, non-universality and/or lack of distinctiveness of the biometric trait, unacceptable error rates, and spoof attacks [2]. Multimodal biometric system employs two or more individual modalities, namely, gait, face, iris and fingerprint, to enhance the recognition accuracy of conventional unimodal methods [3]. The multimodal-based authentication can aid the system in improving the security and effectiveness in comparison of unimodal biometric authentication, and it might become challenging for an adversary to spoof the system owing to two individual biometrics traits. In the Table I various biometric technologies have been compared based on various characteristics. Among all the biometric techniques, today fingerprints and iris are most widely used biometric features for personal identification because of their high acceptability, immutability and individuality. TABLE I COMPARISON OF VARIOUS BIOMETRIC TECHNOLOGIES
I. INTRODUCTION Reliable authorization and authentication has become an integral part of our life for a number of routine applications. Majority of the authentication systems found today are not very flexible (can be broken or stolen) to attacks, rather it can control access to computer systems or secured locations utilizing passwords. Recently in most application areas, biometrics has emerged practically as a better alternative to conventional identification methods. Biometrics, expressed as the science of identifying an individual on the basis of physiological or behavioral traits, seems to achieve acceptance as a suitable method for obtaining an individual’s identity [1]. Some of the biometrics used for authentication is Finger Print, Iris, Palm Print, Hand Signature stroke etc. Biometric technologies have established their importance in a variety of security, access control and monitoring
ISSN : 0975-3397
In this paper, the fingerprint and iris are considered for providing mutual authentication between the server and the user. At first, the fingerprint features are obtained from the fingerprint image using segmentation, orientation field estimation and morphological operators. Likewise, the texture
2652
P.Tamil Selvi et al. / (IJCSE) International Journal on Computer Science and Engineering Vol. 02, No. 08, 2010, 2652-2658 features are acquired from the iris image by segmentation, estimation of iris boundary and normalization. Minutiae points and iris texture, the two extracted features are then fused at feature level to build the multimodal biometric template. Fusion at the feature level is achieved by means of concatenation, shuffling and merging. Thus the user’s finger print and iris images are converted and stored as encrypted binary template, which is used for authentication by the server. Thus the user’s biometric verification data are first transformed into a strong secret and is then stored in the server’s database during registration. During log-in procedure authentication is done both at client side and server side without transmitting the biometric measurement from the user to the server. Further the user and the server communicate with each other with a secret session key that is generated from the biometric for the rest of the transactions. This concept can also be applied to strengthen the existing single server password based authentication systems. II. REVIEW OF RELATED WORK A lot of research has been carried out in the field of Authentication and Key Exchange protocols, which are based on passwords [4]. The Password based user authentication systems are low cost and easy to use but however, the use of passwords has intrinsic weaknesses. The user chosen passwords are inherently weak since most users choose short and easy to remember passwords. In particular, passwords are normally drawn from a relatively small dictionary; thereby prone to Brute-force dictionary attacks, where an attacker enumerates every possible password in the dictionary to determine the actual password. These systems are essentially intended to defeat offline dictionary attacks by outside attackers and assume that the server is completely trusted in protecting the user password database. Once an authentication server is compromised, the attackers perform an offline dictionary attacks against the user passwords. To eliminate this single point of vulnerability inherent in the single-server systems, password systems based on multiple servers were proposed. The principle is distributing the password database as the authentication function to multiple servers, so that an attacker is forced to compromise several servers to be successful in offline dictionary attacks. Recently, Brainard [5] proposed a two-server password system in which one server expose itself to users and the other is hidden from the users. Subsequently, Yang [6] extended and tailored this two server system to the context of federated enterprises, where the back-end server is managed by an enterprise headquarter and each affiliating organization operates a front-end server. Instead of traditional password based systems, biometric techniques are used for mutual authentication and key
ISSN : 0975-3397
generation by Rajeswari Mukesh [7]. It may influenced by some practical issues like noisy sensor data, non-universality and/or lack of distinctiveness of the biometric trait, unacceptable error rates, and spoof attacks. The fusion of fingerprint and iris features for cryptographic key generation is proposed by A.Jagadeesan [8]. The use of multimodal biometrics for key generation provides better security, as it is made difficult for an intruder to spool multiple biometric traits simultaneously. III. PROPOSED APPROACH In the proposed work, the multimodal biometric information is used for mutual authentication and key generation. The use of multimodal biometrics for key generation provides better security, as it is made difficult for an intruder to spool multiple biometric traits simultaneously. This system is a biometric-only system in the sense that it requires no user key cryptosystem and, thus, no Public Key Infrastructure (PKI). This makes the system very attractive considering PKIs are proven to be expensive to deploy in the real world. Moreover, it is suitable for online web applications due to its efficiency in terms of both computation and communication. IV. OVERALL ARCHITECTURE The overall architecture of the multimodal biometric authentication and key exchange system is shown in the Fig.1. The server maintains a database of encrypted minutia template of the user’s finger print and iris. In this setting, users communicate with the server for the purpose of user authentication, by rendering his/her fingerprint and iris, which is transformed into a long secret held by the server in its database.
Hardening of multimodal biometric feature
Biometric Database
Mutual Authentication & Key exchange User 1
Server
User n
Figure 1. Architecture for multimodal biometric authentication
V.
MULTIMODAL BIOMETRICS AUTHENTICATION PROTOCOL
The main part of the protocol design is the defense against offline dictionary attacks by the servers and also to overcome
2653
P.Tamil Selvi et al. / (IJCSE) International Journal on Computer Science and Engineering Vol. 02, No. 08, 2010, 2652-2658 the man-in-the-middle attack done between the user and the server. In any secure system, the user provides his/her fingerprint through a finger scanner. The finger print image undergoes a series of enhancement steps. Likewise iris image also captured and extracted. This is followed by a multimodal hardening protocol with servers to obtain a hardened finger print and iris which are stored into a strong secret. Encrypted storage of the minutia template of the fingerprint and the texture features of iris are done in such a way that they are no longer subjected to offline dictionary attack. During user login, the server using its encrypted fingerprint and iris for user authentication. During authentication, user using fingerprint and iris mutually authenticate each other and negotiate a secret session key. A. Minutiae Points Extraction from Fingerprints A fingerprint is made of a series of ridges and furrows on the surface of the finger. The uniqueness of a fingerprint can be determined by the pattern of ridges and furrows. Minutiae points are local ridge characteristics that occur at either a ridge bifurcation or a ridge ending. A ridge termination is defined as the point where a ridge ends abruptly. A ridge bifurcation is defined as the point where a ridge forks or diverges into branch ridges. The steps involved for minutiae extraction are as follows, 1) Preprocessing: The fingerprint image is first preprocessed by using the methods Histogram equalization and Wiener filtering. Histogram equalization is a very common technique for enhancing the contrast of an image. The basic idea is to map the gray levels based on the probability distribution of the input gray levels [9]. It transforms the intensity values of the image as given in (1),
k k nj S k T rk Pr r j j 1 j 1 n
(1)
where Sk is the intensity value in processed image corresponding to intensity rk in the input image and Pr(rj)= 1,2,…L is the input fingerprint image intensity level. Wiener filtering improves the legibility of the fingerprint without altering its ridge structures [10]. The filter is based on local statistics estimated from a local neighborhood η of size 3 x 3 of each pixel and is given by,
w n1, n2
2
v
2
2
I n1, n2
(2)
where v2 is the noise variance, µ and σ2 are local mean and variance and I represents the gray level intensity in n1, n2 Є η.
ISSN : 0975-3397
2) Segmentation: The fingerprint image obtained after preprocessing is of high contrast and enhanced visibility. The fingerprint image is divided into non-overlapping blocks of size 16 x 16. Subsequently, the gradient of each block is calculated. The standard deviation of gradients in X and Y direction are then computed and summed. If the resultant value is greater than the threshold value the block is filled with ones, else the block is filled with zeros. 3) Orientation Field Estimation: A fingerprint orientation field is defined as the local orientation of the ridge-valley structures [11]. To obtain reliable ridge orientations, the most common approach is based on gradients of gray intensity. In the gradient-based methods, gradient vectors [gx , gy ]T are first calculated by taking the partial derivatives of each pixel intensity in Cartesian coordinates. Traditional gradient-based methods divide the input fingerprint into equal-sized blocks of N x N pixels and average over each block independently. 4) Image Enhancement: The fingerprint image enhancement is achieved by using Gaussian Low-Pass Filter and Gabor Filter. The Gaussian low-pass filter is used as to blur an image. The Gaussian filter generates a `weighted average' of each pixel's neighborhood with the average weighted more towards the value of the central pixels. Because of this, gentler smoothing and edge preserving can be achieved. The Gabor filters have both frequency selective and orientation-selective properties and they also have optimal joint resolution in both spatial and frequency domains. 5) Minutiae extraction: The process of minutiae point extraction is carried out in the enhanced fingerprint image. The steps involved in the extraction process are Binarization and Morphological Operators. Binarization is the process of converting a grey level image into a binary image. It improves the contrast between the ridges and valleys in a fingerprint image and thereby facilitates the extraction of minutiae. The grey level value of each pixel in the enhanced image is examined in the binarization process. If the grey value is greater than the global threshold, then the pixel value is set to a binary value one; or else, it is set to zero. In minutiae extraction algorithms, there are only two levels: the black pixels that denote ridges, and the white pixels that denote valleys. Morphological operators are applied to the binarized fingerprint image. It eliminates the obstacles and noise from the image. Furthermore, the unnecessary spurs, bridges and line breaks are removed by these operators. The process of removal of redundant pixels till the ridges become one pixel wide is facilitated by ridge thinning. The thinning algorithm to a fingerprint image preserves the connectivity of the ridge structures while forming a skeleton version of the binary image.
2654
P.Tamil Selvi et al. / (IJCSE) International Journal on Computer Science and Engineering Vol. 02, No. 08, 2010, 2652-2658 B. Extraction of Features from Iris An annular part between the pupil and the white sclera called the human iris, has an astonishing structure and presents a bounty of interlacing minute characteristics such as freckles, coronas, stripes and more. These perceptible characteristics that are usually called the texture of the iris are unique to every subject [12]. The procedures included in the feature extraction process of the iris image are as follows: 1) Segmentation: Iris segmentation is a significant module in iris recognition since it defines the effective image region utilized for consequent processing such as feature extraction. The iris image is first fed as input to the canny edge detection algorithm that produces the edge map of the iris image for boundary estimation. The exact boundary of pupil and iris is located from the detected edge map using the Hough transform. 2) Iris Normalization: When the iris image is proficiently localized, then the subsequent step is to transform it into the rectangular sized fixed image. Daugman’s Rubber Sheet Model [13] is utilized for the transformation process and is depicted in Figure 2.
yp (θ) = yp0(θ) + rpSin(θ) xi (θ) = xi0 (θ) + riCos(θ) yi (θ) = yi0 (θ) + riSin(θ)
(7) (8) (9)
where, (xp , yp ) and (xi , yi ) are the coordinates on the pupil and iris boundaries along the direction. (xp0, yp0), (xi0 , yi0 ) are the coordinates of pupil and iris centers [14]. 3) Extraction of iris texture: The normalized 2D form image is disintegrated up into 1D signal, and these signals are made use to convolve with 1D Gabor wavelets. The frequency response of a Log-Gabor filter is as follows, 2 lo g f f 0 G f ex p 2 2 log f 0
(10)
where f0 indicates the centre frequency, and σ provides the bandwidth of the filter. The Log-Gabor filter outputs the biometric feature of the iris.
C. Feature Level Fusion of Fingerprint and Iris Features There are two sets of features used for fusion. They are Fingerprint features and Iris features. The next step is to fuse the two sets of features at the feature level to obtain a multimodal biometric template that can perform biometric authentication.
Figure 2. Daugman’s Rubber Sheet Model
On polar axes, for each pixel in the iris, its equivalent position is found out. This process consists of two resolutions. They are Radial resolution and Angular resolution. The former is the number of data points in the radial direction where as, the later part is the number of radial lines produced around iris region. Utilizing the following equation, the iris region is transformed to a 2D array by making use of horizontal dimensions of angular resolution and vertical dimension of radial resolution. I[x(r, θ), y(r, θ )] I (r, θ )
(3)
where, I (x, y) is the iris region, (x, y) and (r, θ) are the Cartesian and normalized polar coordinates respectively. The range of θ is [0 2π] and r is [0 1]. x(r, θ ) and y(r, θ) are described as linear combinations set of pupil boundary points. To perform the transformation, the formulas are given in (4) to (9). x(r, θ) = (1- r)xp (θ) + xi (θ) y(r, θ) = (1- r)yp (θ) + yi (θ) xp (θ) = xp0(θ) + rpCos(θ)
ISSN : 0975-3397
(4) (5) (6)
Each minutiae point extracted from a fingerprint is represented as ( x , y ) coordinates. In this we store those extracted minutiae points in two different vectors: Vector F1 contains all the x co-ordinate values and Vector F2 contains all the y co-ordinate values. F1 = [ x1 x2 x3 ……xn ] ; | F1 | = n F2 = [ y1 y2 y3 ……yn ] ; | F2 | = n
(11) (12)
The texture properties obtained from the log-gabor filter are complex numbers (a + ib). Similar to fingerprint representation, we also store the iris texture features in two different vectors: Vector I1 contains the real part of the complex numbers and Vector I2 contains the imaginary part of the complex numbers. I1 = [ a1 a2 a3 ……am ] ; | I1 | = m I2 = [ b1 b2 b3 ……bm ] ; | I2 | = m
(13) (14)
Thereby, the input to the fusion process will be four vectors F1, F2, I1, and I2. The fusion process results with the multimodal biometric template. The steps involved in fusion of biometric feature vectors are as follows. 1) Shuffling of individual feature vectors: The first step in the fusion process is the shuffling of each of the individual
2655
P.Tamil Selvi et al. / (IJCSE) International Journal on Computer Science and Engineering Vol. 02, No. 08, 2010, 2652-2658 feature vectors F1, F2, I1 and I2. The steps involved in the shuffling of vector F1 are,
c) The resultant binary value is then converted back into decimal form.
Step 1: A random vector R of size F1 is generated. The random vector R is controlled by the seed value.
Step 2: These decimal values are stored in the vector BT , which serves multimodal biometric template.
Step 2: For shuffling the ith component of fingerprint feature vector F1, a)
The i component of the random vector R is multiplied with a large integer value.
b) The product value obtained is modulo operated with the size of the fingerprint feature vector F1. c)
VI.
MULTIMODAL HARDENING PROTOCOL
th
The resultant value is the index say ‘ j ’ to be interchanged with. The components in the ith and jth indexes are interchanged.
Step 3: Step (2) is repeated for every component of F1 . The shuffled vector F1 is represented as S1 . The above process is repeated for every other vectors F2, I1 and I2 with S1, S2 and S3 as random vectors respectively, where S2 is shuffled F2 and S3 is shuffled I1 . The shuffling process results with four vectors S1, S2 , S3 and S4 . 2) Concatenation of shuffled feature vectors: The next step is to concatenate the shuffled vectors process S1 , S2, S3 and S4. Here, we concatenate the shuffled fingerprints S1 and S2 with the shuffled iris features S3 and S4 respectively. The concatenation of the vectors S1 and S3 is carried out as follows:
The following computations take place at the user side during registration process: 1) The user is asked to give the fingerprint input at least five times and the similar minutia is extracted to form minutia template (FP). Alike from many iris images of the user the similar iris features are extracted to form the iris template (IF). The combined feature template is computed and it is said to be Combined Multimodal Features (CMF). 2) The user then encrypts the minutia template using AES-128 bit symmetric cipher in ECB mode. 3) The user then sends (UID, EAES(CMF)) to the server for storage in its database. Thus the Implementation of multimodal hardening protocol leads to the generation of Strong secret. VII.
MULTIMODAL AUTHENTICATION PROTOCOL
The Algorithm makes the following Assumptions:
Step 1: A vector M1 of size |S1| + |S2| is created and its first |S3| values are filled with S3 .
1) Let p, q be two large prime numbers such that p = 2q + 1.
Step 2: For every component S1 ,
2) Let g Î QRp are of order q where QRp is the group of quadratic residues modulo p.
a) The corresponding indexed component of M1 ‘ t ’is chosen.
say
b) Logical right shift operation is carried in M1 from index ‘ t ’. c) The component of S1 is inserted into the emptied tth index of M1 . The aforesaid process is carried out between shuffled vectors S2 and S4 to form vector M2. Thereby, the concatenation process results with two vectors M1 and M2. 3) Merging of the concatenated feature vectors: The last step in generating the multimodal biometric template BT is the merging of two vectors M1 and M2. The steps involved in the merging process are as follows: Step 1: For every component of M1 and M2 , a) The components M11 and M21 are converted their binary form.
into
b) Binary NOR operation is performed between the components M11 and M21 .
ISSN : 0975-3397
The outline of the multimodal Authentication protocol is given below to enable mutual authentication and key exchange between the User and the Server. Step 1: To initiate a request for service, user computes MB1 = EAES(CMF). Step 2: The user Computes B1 ≡ gMB1 (mod p). The user sends the user ID along with B1 to the server. Step 3: Server selects the encrypted minutia template with the user-Id using a table look-up procedure and computes B2 ≡ gMB2 (mod p), where MB2 is the encrypted minutiae template stored at the server side during registration. Then the server compares whether B1 ≡ B2 (mod p). If it holds the server is assured of the authenticity of the user otherwise aborts the authentication protocol. Then the server sends B2 to the user. Step 4: Upon reception of B2 , User verifies whether B1≡ B2 (mod p). If so authenticated otherwise aborts the
2656
P.Tamil Selvi et al. / (IJCSE) International Journal on Computer Science and Engineering Vol. 02, No. 08, 2010, 2652-2658 authentication protocol. If authenticated the user computes the session key by using the formula, Ks = HSHA1 ( UID, MB1)
(15)
Step 5: Simultaneously the server also generates the session key using the formula, Ks = HSHA1 ( UID, MB2 )
(16)
These steps are performed for avoiding the dictionary attack from an outside attacker.
VIII.
11010010011001001011000110010011010011001100101100 110110 Figure 5. Generated 256 bit key
The encryption using AES encryption algorithm is applied and the encrypted key is saved secure in the server and which avoids the dictionary attack. The multimodal hardening protocol and the multimodal authentication protocol is applied for the secure sharing of the cryptographic key.
EXPERIMENTAL RESULTS
The experimental results of the proposed approach are presented in this section. The designed proposed system is experimented with the Matlab (Matlab7.4). For experimentation, the fingerprint images from publicly available databases are used and the iris images from CASIA Iris Image Database collected by Institute of Automation, Chinese Academy of Science. The proposed approach is tested with different sets of input images. For every input fingerprint image, the extracted minutiae points and the intermediate results of the proposed approach are shown in Figure 3. Similarly, for iris images, the intermediate results such as the image with located pupil and iris boundary, the image with detected top eyelid region and the normalized iris image are given in Figure 4. Then, the 256 bit cryptographic key generated from the fingerprint and iris images using the proposed approach is presented in Figure 5.
A. Strength of the protocol The analysis for the security of the protocol is based on the following Deffie-Hellman assumptions [15]: Assumption 1: For a cyclic group G, generated by g, we are given g and gn, n Є N, the challenge is to compute n. Assumption 2: Given g, ga, gb, it is hard to compute gab. The relationship between these two assumptions has been extensively studied. It is clear that assumption 2 will not be satisfied in a group where finding a discrete logarithm solution is easy In Maurer and Wolf(1999), Boneh and Lipton (1996), the authors show that in several settings the validity of assumption 2 and the hardness of the discrete logarithm problem are in fact equivalent. IX. CONCLUSION
(a)
(b)
(c)
(d)
Figure 3. (a) Input fingerprint image (b) Segmented image (c) Enhanced fingerprint image (d) Fingerprint image with minutiae points
This Multimodal Biometric Authentication and key exchange system together with its practical applications offers many appealing performance features. The salient features of this proposal make it a suitable candidate for number of practical applications like Biometric ATMs, Biometric online web applications etc. Compared with previous solutions, our system possesses many advantages, such as the secure against dictionary attack, avoidance of PKI, and high efficiency in terms of both computation and communications. In this system, we have reused ideas in the areas of image processing technique to extract the minutiae from biometric image. Therefore it can be directly applied to fortify existing standard single-server biometric based security applications. REFERENCES
(a)
(b)
(c)
(d)
Figure 4. (a) Input iris image (b) Located pupil and iris boundary (c) Detected top and bottom eyelid region (d) Normalized iris image
01111011111110100100100100100000000000111111111111 01010001010001001000110110111101111111010010010010 01000000000001111111111110101000101000100100011011 01101000100010001001001010110110001001101011011000
ISSN : 0975-3397
[1] Arun Ross and Anil K. Jain, "Multimodal Biometrics: An Overview", in proceedings of the 12th European Signal Processing Conference, pp. 1221-1224, 2004. [2] A.K. Jain and A. Ross, “Multi-biometric systems: special issue on multimodal interfaces that flex, adapt, and persist”, Communications of the ACM, vol. 47, no. 1, pp. 34–40, 2004. [3] L.Hong, and A.K.Jain “Can multibiometrics improve performance?”, in Proceedings of IEEE Workshop on Automatic Identification Advanced Technologies, pp. 59–64, NJ, USA, 1999.
2657
P.Tamil Selvi et al. / (IJCSE) International Journal on Computer Science and Engineering Vol. 02, No. 08, 2010, 2652-2658 [4] M.Bellare, D. Pointcheval, and P. Rogaway, “Authenticated Key Exchange Secure Against Dictionary Attacks,” Advances in Cryptology Eurocrypt ’00, 2000 pp. 139-155. [5] J. Brainard, A. Juels, B. Kaliski, and M. Szydlo, “A New Two – Server Approach for Authentication with Short Secrets,” Proc. USENIX Security Symp., 2003. [6] Y.J. Yang, F. Bao, and R.H. Deng, “A New Architecture for Authentication and Key Exchange Using Password for Federated Enterprises, ” Proc. 20th Int’l Federation for Information Processing Int’l Information Security Conf. (SEC ’05), 2005 [7] Rajeswari Mukesh, A. Damodaram, V. Subbiah Bharathi, “Finger Print Based Authentication and Key Exchange System Secure Against Dictionary Attack”, IJCSNS International Journal of Computer Science and Network Security, VOL.8 No.10, October 2008. [8] A. Jagadeesan, Dr. K. Duraiswamy, “Secured Cryptographic Key Generation From Multimodal Biometrics: Feature Level Fusion of Fingerprint and Iris”, (IJCSIS) International Journal of Computer Science and Information Security, Vol. 7, No. 2, February 2010. [9] Balasubramanian .K and Babu. P, "Extracting Minutiae from Fingerprint Images using Image Inversion and Bi-Histogram Equalization", Proceedings of SPIT-IEEE Colloquium and International Conference, Mumbai, India. [10] Greenberg, S. Aladjem, M. Kogan, D and Dimitrov, “Fingerprint image enhancement using filtering techniques” in Proceedings of the 15th International Conference on Pattern Recognition, vol.32, pp. 322325, Barcelona, Spain, 2000. [11] Jinwei Gu and Jie Zhou, “A Novel Model for Orientation Field of Fingerprints”, in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol.2, 2003. [12] J. Daugman, “Statistical Richness of Visual Phase Information: Update on Recognizing Persons by Iris Patterns,” International Journal of Computer Vision, vol. 45, no. 1, pp. 25-38, 2001. [13] John Daugman, “How Iris Recognition Works”, in Proceedings of International Conference on Image Processing, vol.1, pp. I-33- I-36, 2002. [14] S. Uma Maheswari, P. Anbalagan and T.Priya, “ Efficient Iris Recognition through Improvement in Iris Segmentation Algorithm”, International Journal on Graphics, Vision and Image Processing, vol. 8, no.2, pp. 29-35, 2008. [15] D. Boneh,“The Decision Diffie-Hellman Problem,” Proc. Third Int’l Algorithmic Number Theory Symp., pp. 48-63, 1998.
AUTHOR PROFILE P. Tamil Selvi received MCA degree in Bharathiar university and currently pursuing M.Phil in P.S.G.R.Krishnammal college for women affiliated under Bharathiar university. Her area of interest is Network security. N.Radha pursuing Ph.D in network security. She had more than ten years of teaching experience. Her area of interest are Oops, Network security. She presented and published the papers in various national and international conference and journals.
ISSN : 0975-3397
2658
